PulseAugur
LIVE 13:02:50
research · [2 sources] ·
0
research

HEXST Transformer predicts spatial gene expression from histology slides

Researchers have developed HEXST, a novel Transformer model designed to predict gene expression from histology slides. This model addresses limitations in existing methods by accounting for the hexagonal sampling patterns common in spatial transcriptomics platforms and employing a contrast-sensitive objective to preserve spatial heterogeneity. HEXST demonstrates superior performance across multiple datasets compared to current state-of-the-art approaches. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces a novel geometric approach to Transformer attention for biological data analysis, potentially improving diagnostic accuracy in pathology.

RANK_REASON This is a research paper detailing a new model and its performance on specific datasets.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Keunho Byeon, Jin Tae Kwak ·

    HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression Prediction

    arXiv:2605.04682v1 Announce Type: new Abstract: Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend this capability to routine practice, recent computation…

  2. arXiv cs.CV TIER_1 · Jin Tae Kwak ·

    HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression Prediction

    Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend this capability to routine practice, recent computational methods aim to infer spatial gene expression …